Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    identifiers or variables related to mathematical or scientific expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    initComponents
    -0.74
    <eos>
    -0.58
     Balak
    -0.56
    ↵↵
    -0.51
    ecake
    -0.51
     Pres
    -0.50
     становника
    -0.50
    immel
    -0.49
    ToFile
    -0.49
    bės
    -0.49
    POSITIVE LOGITS
     itſelf
    0.91
    verifyException
    0.79
    Искәрмәләр
    0.72
     beginnetje
    0.71
    apimachinery
    0.70
     onely
    0.70
     Bathurst
    0.70
     nahilalakip
    0.70
     whoſe
    0.69
     ſche
    0.68
    Act Density 0.072%

    No Known Activations